agentbook-version-control

agentbook-version-control is a skill for Claude Code, Codex from NovasPlace/CSM. It costs 65 tokens per session (939 once invoked), scanned A, original, MIT.

Instructions for coordinating Git, a system that tracks file changes, with AgentBook, a record of an agent's decisions, evidence, and recovery state. It covers status checks, checkpoints, history, and handoffs between work sessions.

In plain words
What is it for?
Use it before and after risky or branching changes, when resuming work, comparing approaches, recording tests, or handing a task to another agent.
Why use it?
It helps preserve why changes were made and what was verified, while keeping the actual files and commits under Git's control.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/novasplace/csm/agentbook-version-control
Any agent
npx skills add NovasPlace/CSM --skill agentbook-version-control
Clone the repo
git clone --depth 1 https://github.com/NovasPlace/CSM

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agentbook-version-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/novasplace/csm/agentbook-version-control.svg)](https://agentmods.dev/skills/novasplace/csm/agentbook-version-control)
Your own site
<a href="https://agentmods.dev/skills/novasplace/csm/agentbook-version-control"><img src="https://agentmods.dev/badge/skills/novasplace/csm/agentbook-version-control.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 939 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.00939
Opus 5 $0.00032 $0.00469
Sonnet 5 $0.00013 $0.00188
Haiku 4.5 $0.00006 $0.00094

Measured 5d ago against content hash 3faa1f8117d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentbook-version-control scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cross-session-memory-bridge/skills/agentbook-version-control/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentBook Version Control

Treat Git as the authority for files and AgentBook as the provenance layer for intent, evidence, decisions, tests, and recovery state. Never represent AgentBook as a replacement for Git.

Establish status

  1. Inspect the current workspace, git status, and recent Git history before trusting recalled state.
  2. Before the first CSM operation, call csm_runtime_status. Stop and report a provider or project-root mismatch.
  3. Read csm_agentbook_state, recent csm_agentbook_events, goal_list, and list_checkpoints as needed.
  4. Report status using five fields: workspace identity, active goal, latest checkpoint, verified evidence, and unresolved work.

Current files and test output outrank memory. Treat automatic event capture as a recovery log, not as a curated milestone.

Create a checkpoint

Create a checkpoint before an expensive, risky, or branching change and after a verified outcome. Include this information in the explicit message snapshot or milestone used to build it:

goal:
parent/baseline:
git commit:
dirty-tree status or diff hash:
change:
reason:
expected effect:
verification:
actual result:
decision: keep | revert | unresolved
known risks:
next action:

Use create_checkpoint for recoverable session state. Use bridge_sync_turn only for a durable milestone that automatic hooks cannot infer. Do not create redundant checkpoints for routine reads.

Branch and compare work

  • Use Git branches or worktrees for file isolation. Do not invent a second source-control system.
  • Give each agent attempt one explicit goal, baseline Git identity, and checkpoint lineage note.
  • Keep parallel attempts disjoint where possible. Never merge or delete a branch without the user's authorization.
  • Compare attempts across code and agent state: file diff, decisions, evidence, tests, performance, cost, failures, and open risks.
  • Apply only the selected artifacts through normal Git operations. Record why the result was kept, combined, or rejected.

Read the full file on GitHub · 97 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 97 lines · 65 tokens per session scan A 3faa1f8117d4

Subscribe to this mod's changes

agentbook-version-control is a skill published in the GitHub repository NovasPlace/CSM (42 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 939 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dark-memory

Use for governance, memory, drift detection, and audit trail via dark-memory-mcp. Covers 52 canonical + 3 red-team tools across 16 namespaces: session lifecycle, agentmemory CRUD+search, vibe-flow spec/artifact publish + drift, LLM-as-judge, delegation+mindset, research, observability, error observatory, governance…

Opita-Code/dark-memory-mcp · 353 tokens

mem9

Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.

mem9-ai/mem9 · 27 tokens

usage

Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics…

Canner/WrenAI · 156 tokens

ai-chat

Guidance for improving the Windmill AI chat (copilot), especially global mode — tools, prompts, and context-window discipline. Use when editing chat tools, system prompts, or tool-result shapes under frontend/src/lib/components/copilot/chat, or when changing how the chat manages its context window.

windmill-labs/windmill · 62 tokens

kip-cognitive-nexus

Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update persistent memory, especially for: remembering user…

ldclabs/KIP · 90 tokens

mstar-compound-refresh

Morning Star 知识维护与项目知识 bootstrap —— 审查 {KNOWLEDGEDIR} 文档是否仍准确、去重叠合并、清理过期知识;或从代码库提炼 CONCEPTS.md、基线 knowledge 脚手架(无/残旧/空白 knowledge)。STRATEGY.md 创建委托 mstar-strategy。触发:mstar-compound 发现可合并文档、定期维护、项目缺 CONCEPTS.md/{KNOWLEDGEDIR}、stale knowledge scaffolding、显式 bootstrap 请求、或显式 refresh。产出:更新/合并/删除知识文档 + 维护报告;或 bootstrap…

btspoony/mstar-harness · 174 tokens